Deep Learning Surrogates for Real-Time Gas Emission Inversion

TL;DR

This paper presents a deep learning surrogate model integrated into a Bayesian inversion framework for real-time gas emission source identification, achieving high accuracy and speed in complex environmental conditions.

Contribution

It introduces a novel spatio-temporal inversion method using a deep-learning CFD surrogate within a Bayesian framework for rapid emission source estimation.

Findings

Comparable accuracy to CFD and Gaussian plume models

Orders-of-magnitude faster runtimes

Robust performance in obstructed-flow scenarios

Abstract

Real-time identification and quantification of greenhouse-gas emissions under transient atmospheric conditions is a critical challenge in environmental monitoring. We introduce a spatio-temporal inversion framework that embeds a deep-learning surrogate of computational fluid dynamics (CFD) within a sequential Monte Carlo algorithm to perform Bayesian inference of both emission rate and source location in dynamic flow fields. By substituting costly numerical solvers with a multilayer perceptron trained on high-fidelity CFD outputs, our surrogate captures spatial heterogeneity and temporal evolution of gas dispersion, while delivering near-real-time predictions. Validation on the Chilbolton methane release dataset demonstrates comparable accuracy to full CFD solvers and Gaussian plume models, yet achieves orders-of-magnitude faster runtimes. Further experiments under simulated obstructed-flow scenarios confirm robustness in complex environments. This work reconciles physical fidelity with computational feasibility, offering a scalable solution for industrial emissions monitoring and other time-sensitive spatio-temporal inversion tasks in environmental and scientific modeling.